Construct Single-Hierarchical P/NBD Model for Short Timeframe Synthetic Data

Author

Mick Cooney

Published

November 11, 2023

In this workbook we construct the non-hierarchical P/NBD models on the synthetic data with the longer timeframe.

0.1 Load Short-Timeframe Synthetic Transaction Data

We now want to load the CD-NOW transaction data.

Code
customer_cohortdata_tbl <- read_rds("data/shortsynth_customer_cohort_data_tbl.rds")
customer_cohortdata_tbl |> glimpse()
Rows: 5,000
Columns: 5
$ customer_id     <chr> "SFC202001_0001", "SFC202001_0002", "SFC202001_0003", …
$ cohort_qtr      <chr> "2020 Q1", "2020 Q1", "2020 Q1", "2020 Q1", "2020 Q1",…
$ cohort_ym       <chr> "2020 01", "2020 01", "2020 01", "2020 01", "2020 01",…
$ first_tnx_date  <dttm> 2020-01-01 02:15:58, 2020-01-01 00:40:17, 2020-01-01 …
$ total_tnx_count <int> 3, 9, 1, 2, 5, 1, 4, 6, 2, 4, 1, 11, 3, 3, 1, 1, 11, 3…
Code
customer_transactions_tbl <- read_rds("data/shortsynth_transaction_data_tbl.rds")
customer_transactions_tbl |> glimpse()
Rows: 29,454
Columns: 7
$ customer_id   <chr> "SFC202001_0002", "SFC202001_0001", "SFC202001_0004", "S…
$ tnx_timestamp <dttm> 2020-01-01 00:40:17, 2020-01-01 02:15:58, 2020-01-01 18…
$ tnx_dow       <fct> Wed, Wed, Wed, Wed, Thu, Thu, Thu, Thu, Thu, Thu, Thu, F…
$ tnx_month     <fct> Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, Jan, J…
$ tnx_week      <chr> "00", "00", "00", "00", "00", "00", "00", "00", "00", "0…
$ invoice_id    <chr> "T20200101-0001", "T20200101-0002", "T20200101-0003", "T…
$ tnx_amount    <dbl> 51.73, 139.05, 11.72, 88.30, 1.16, 0.95, 127.85, 35.07, …
Code
customer_subset_id <- read_rds("data/shortsynth_customer_subset_ids.rds")
customer_subset_id |> glimpse()
 Factor w/ 5000 levels "SFC202001_0002",..: 2 3 8 10 14 16 17 21 25 27 ...

We re-produce the visualisation of the transaction times we used in previous workbooks.

Code
plot_tbl <- customer_transactions_tbl |>
  group_nest(customer_id, .key = "cust_data") |>
  filter(map_int(cust_data, nrow) > 3) |>
  slice_sample(n = 30) |>
  unnest(cust_data)

ggplot(plot_tbl, aes(x = tnx_timestamp, y = customer_id)) +
  geom_line() +
  geom_point() +
  labs(
      x = "Date",
      y = "Customer ID",
      title = "Visualisation of Customer Transaction Times"
    ) +
  theme(axis.text.y = element_text(size = 10))

0.2 Load Derived Data

Code
obs_fitdata_tbl   <- read_rds("data/shortsynth_obs_fitdata_tbl.rds")
obs_validdata_tbl <- read_rds("data/shortsynth_obs_validdata_tbl.rds")

customer_fit_stats_tbl <- obs_fitdata_tbl |>
  rename(x = tnx_count)

0.3 Load Subset Data

We also want to construct our data subsets for the purposes of speeding up our valuations.

Code
customer_fit_subset_tbl <- obs_fitdata_tbl |>
  filter(customer_id %in% customer_subset_id)

customer_fit_subset_tbl |> glimpse()
Rows: 1,000
Columns: 6
$ customer_id    <fct> SFC202001_0001, SFC202001_0004, SFC202001_0008, SFC2020…
$ first_tnx_date <dttm> 2020-01-01 02:15:58, 2020-01-01 18:04:32, 2020-01-02 1…
$ last_tnx_date  <dttm> 2020-02-20 14:43:57, 2020-01-10 17:49:12, 2020-07-17 0…
$ tnx_count      <dbl> 2, 1, 5, 4, 0, 10, 10, 0, 0, 0, 6, 2, 0, 0, 0, 1, 0, 3,…
$ t_x            <dbl> 7.2170614, 1.2841927, 28.0650995, 12.3070761, 0.0000000…
$ T_cal          <dbl> 104.4151, 104.3210, 104.1918, 104.1751, 104.0693, 104.0…
Code
customer_valid_subset_tbl <- obs_validdata_tbl |>
  filter(customer_id %in% customer_subset_id)

customer_valid_subset_tbl |> glimpse()
Rows: 1,000
Columns: 3
$ customer_id       <fct> SFC202001_0001, SFC202001_0004, SFC202001_0008, SFC2…
$ tnx_count         <dbl> 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0…
$ tnx_last_interval <dbl> NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, NA, …

We now use these datasets to set the start and end dates for our various validation methods.

Code
dates_lst <- read_rds("data/shortsynth_simulation_dates.rds")

use_fit_start_date <- dates_lst$use_fit_start_date
use_fit_end_date   <- dates_lst$use_fit_end_date

use_valid_start_date <- dates_lst$use_valid_start_date
use_valid_end_date   <- dates_lst$use_valid_end_date

Before we start on that, we set a few parameters for the workbook to organise our Stan code.

Code
stan_modeldir <- "stan_models"
stan_codedir  <-   "stan_code"

1 Fit First Hierarchical Lambda Model

Our first hierarchical model puts a hierarchical prior around the mean of our population \(\lambda\) - lambda_mn.

Once again we use a Gamma prior for it.

1.1 Compile and Fit Stan Model

We now compile this model using CmdStanR.

Code
pnbd_onehierlambda_stanmodel <- cmdstan_model(
  "stan_code/pnbd_onehier_lambda.stan",
  include_paths =   stan_codedir,
  pedantic      =           TRUE,
  dir           =  stan_modeldir
  )

We then use this compiled model with our data to produce a fit of the data.

Code
stan_modelname <- "pnbd_short_onehierlambda1"
stanfit_prefix <- str_c("fit_", stan_modelname)
stanfit_seed   <- stanfit_seed + 1

stanfit_object_file <- glue("data/{stanfit_prefix}_stanfit.rds")


stan_data_lst <- customer_fit_stats_tbl |>
  select(customer_id, x, t_x, T_cal) |>
  compose_data(
    hier_lambda_mn_p1 = 0.25,
    hier_lambda_mn_p2 = 1,

    lambda_cv = 1.00,
    
    mu_mn     = 0.10,
    mu_cv     = 1.00,
    )

if(!file_exists(stanfit_object_file)) {
  pnbd_short_onehierlambda1_stanfit <- pnbd_onehierlambda_stanmodel$sample(
    data            =                stan_data_lst,
    chains          =                            4,
    iter_warmup     =                          500,
    iter_sampling   =                          500,
    seed            =                 stanfit_seed,
    save_warmup     =                         TRUE,
    output_dir      =                stan_modeldir,
    output_basename =               stanfit_prefix,
    )
  
  pnbd_short_onehierlambda1_stanfit$save_object(stanfit_object_file, compress = "gzip")

} else {
  pnbd_short_onehierlambda1_stanfit <- read_rds(stanfit_object_file)
}

pnbd_short_onehierlambda1_stanfit$summary()
# A tibble: 9,963 × 10
   variable       mean   median      sd     mad       q5      q95  rhat ess_bulk
   <chr>         <num>    <num>   <num>   <num>    <num>    <num> <num>    <num>
 1 lp__       -4.69e+4 -4.69e+4 6.41e+1 6.29e+1 -4.70e+4 -4.68e+4 1.00      546.
 2 lambda_mn   2.49e-1  2.49e-1 5.85e-3 5.82e-3  2.39e-1  2.59e-1 1.00     1519.
 3 lambda[1]   4.36e-1  4.20e-1 1.47e-1 1.43e-1  2.24e-1  7.05e-1 1.00     2862.
 4 lambda[2]   2.08e-1  1.78e-1 1.32e-1 1.16e-1  5.03e-2  4.70e-1 0.999    2869.
 5 lambda[3]   2.58e-1  2.09e-1 2.06e-1 1.62e-1  4.02e-2  6.44e-1 1.00     2587.
 6 lambda[4]   1.37e-1  8.24e-2 1.63e-1 9.40e-2  4.90e-3  4.42e-1 1.00     1750.
 7 lambda[5]   4.86e-1  4.41e-1 2.65e-1 2.40e-1  1.47e-1  9.86e-1 1.00     2470.
 8 lambda[6]   2.40e-1  1.90e-1 1.96e-1 1.53e-1  3.21e-2  6.21e-1 1.00     1973.
 9 lambda[7]   1.43e-1  8.11e-2 1.73e-1 9.21e-2  5.69e-3  4.92e-1 1.00     2591.
10 lambda[8]   1.62e-1  1.54e-1 7.04e-2 6.59e-2  6.86e-2  2.95e-1 1.00     2095.
# ℹ 9,953 more rows
# ℹ 1 more variable: ess_tail <num>

We have some basic HMC-based validity statistics we can check.

Code
pnbd_short_onehierlambda1_stanfit$cmdstan_diagnose()
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda1-1.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda1-2.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda1-3.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda1-4.csv not found
No valid input files, exiting.

1.2 Visual Diagnostics of the Sample Validity

Now that we have a sample from the posterior distribution we need to create a few different visualisations of the diagnostics.

Code
parameter_subset <- c(
  "lambda_mn",
  "lambda[1]", "lambda[2]", "lambda[3]", "lambda[4]",
  "mu[1]",     "mu[2]",     "mu[3]",     "mu[4]"
  )

pnbd_short_onehierlambda1_stanfit$draws(inc_warmup = FALSE) |>
  mcmc_trace(pars = parameter_subset) +
  expand_limits(y = 0) +
  labs(
    x = "Iteration",
    y = "Value",
    title = "Traceplot of Sample of Lambda and Mu Values"
    ) +
  theme(axis.text.x = element_text(size = 10))

We also check \(N_{eff}\) as a quick diagnostic of the fit.

Code
pnbd_short_onehierlambda1_stanfit |>
  neff_ratio(pars = c("lambda", "mu")) |>
  mcmc_neff() +
    ggtitle("Plot of Parameter Effective Sample Sizes")

1.3 Assess the Model

As we intend to run the same logic to assess each of our models, we have combined all this logic into a single function run_model_assessment, to run the simulations and combine the datasets.

Code
pnbd_stanfit <- pnbd_short_onehierlambda1_stanfit |>
  recover_types(customer_fit_stats_tbl)

pnbd_short_onehierlambda1_assess_data_lst <- run_model_assessment(
  model_stanfit    = pnbd_stanfit,
  insample_tbl     = customer_fit_subset_tbl,
  fit_label        = "pnbd_short_onehierlambda1",
  fit_end_dttm     = use_fit_end_date     |> as.POSIXct(),
  valid_start_dttm = use_valid_start_date |> as.POSIXct(),
  valid_end_dttm   = use_valid_end_date   |> as.POSIXct(),
  sim_seed         = 4210
  )

pnbd_short_onehierlambda1_assess_data_lst |> glimpse()
List of 5
 $ model_fit_index_filepath     : 'glue' chr "data/pnbd_short_onehierlambda1_assess_fit_index_tbl.rds"
 $ model_valid_index_filepath   : 'glue' chr "data/pnbd_short_onehierlambda1_assess_valid_index_tbl.rds"
 $ model_simstats_filepath      : 'glue' chr "data/pnbd_short_onehierlambda1_assess_model_simstats_tbl.rds"
 $ model_fit_simstats_filepath  : 'glue' chr "data/pnbd_short_onehierlambda1_assess_fit_simstats_tbl.rds"
 $ model_valid_simstats_filepath: 'glue' chr "data/pnbd_short_onehierlambda1_assess_valid_simstats_tbl.rds"

1.3.1 Check In-Sample Data Validation

We first check the model against the in-sample data.

Code
simdata_tbl <- pnbd_short_onehierlambda1_assess_data_lst |>
  use_series(model_fit_simstats_filepath) |>
  read_rds()

insample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_fit_subset_tbl,
  simdata_tbl = simdata_tbl
  )

insample_plots_lst$multi_plot |> print()

Code
insample_plots_lst$total_plot |> print()

Code
insample_plots_lst$quant_plot |> print()

This fit looks reasonable and appears to capture most of the aspects of the data used to fit it. Given that this is a synthetic dataset, this is not surprising, but at least we appreciate that our model is valid.

1.3.2 Check Out-of-Sample Data Validation

We now repeat for the out-of-sample data.

Code
simdata_tbl <- pnbd_short_onehierlambda1_assess_data_lst |>
  use_series(model_valid_simstats_filepath) |>
  read_rds()

outsample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_valid_subset_tbl,
  simdata_tbl = simdata_tbl
  )

outsample_plots_lst$multi_plot |> print()

Code
outsample_plots_lst$total_plot |> print()

Code
outsample_plots_lst$quant_plot |> print()

As for our short time frame data, overall our model is working well.

2 Fit Second Hierarchical Lambda Model

In this model, we are going with a broadly similar model but we are instead using a different mean for our hierarchical prior.

2.1 Fit Stan Model

We now want to fit the model to our data using this alternative prior for lambda_mn.

Code
stan_modelname <- "pnbd_short_onehierlambda2"
stanfit_prefix <- str_c("fit_", stan_modelname)
stanfit_seed   <- stanfit_seed + 1

stanfit_object_file <- glue("data/{stanfit_prefix}_stanfit.rds")


stan_data_lst <- customer_fit_stats_tbl |>
  select(customer_id, x, t_x, T_cal) |>
  compose_data(
    hier_lambda_mn_p1 = 0.50,
    hier_lambda_mn_p2 = 1,

    lambda_cv = 1.00,
    
    mu_mn     = 0.10,
    mu_cv     = 1.00,
    )

if(!file_exists(stanfit_object_file)) {
  pnbd_short_onehierlambda2_stanfit <- pnbd_onehierlambda_stanmodel$sample(
    data            =                stan_data_lst,
    chains          =                            4,
    iter_warmup     =                          500,
    iter_sampling   =                          500,
    seed            =                 stanfit_seed,
    save_warmup     =                         TRUE,
    output_dir      =                stan_modeldir,
    output_basename =               stanfit_prefix,
    )
  
  pnbd_short_onehierlambda2_stanfit$save_object(stanfit_object_file, compress = "gzip")

} else {
  pnbd_short_onehierlambda2_stanfit <- read_rds(stanfit_object_file)
}

pnbd_short_onehierlambda2_stanfit$summary()
# A tibble: 9,963 × 10
   variable       mean   median      sd     mad       q5      q95  rhat ess_bulk
   <chr>         <num>    <num>   <num>   <num>    <num>    <num> <num>    <num>
 1 lp__       -4.69e+4 -4.69e+4 6.25e+1 6.34e+1 -4.70e+4 -4.68e+4  1.01     621.
 2 lambda_mn   2.49e-1  2.49e-1 5.73e-3 5.83e-3  2.40e-1  2.58e-1  1.00    1376.
 3 lambda[1]   4.39e-1  4.18e-1 1.48e-1 1.52e-1  2.31e-1  7.07e-1  1.00    2541.
 4 lambda[2]   2.08e-1  1.78e-1 1.38e-1 1.22e-1  4.66e-2  4.68e-1  1.00    2096.
 5 lambda[3]   2.62e-1  2.12e-1 2.02e-1 1.67e-1  3.95e-2  6.66e-1  1.00    1713.
 6 lambda[4]   1.42e-1  7.80e-2 1.80e-1 9.11e-2  4.21e-3  4.97e-1  1.00    1891.
 7 lambda[5]   4.91e-1  4.38e-1 2.70e-1 2.52e-1  1.44e-1  1.01e+0  1.00    2188.
 8 lambda[6]   2.45e-1  1.89e-1 1.99e-1 1.54e-1  3.13e-2  6.42e-1  1.00    2137.
 9 lambda[7]   1.40e-1  8.29e-2 1.68e-1 9.21e-2  5.23e-3  4.52e-1  1.00    1787.
10 lambda[8]   1.62e-1  1.55e-1 6.98e-2 6.98e-2  6.76e-2  2.87e-1  1.00    2572.
# ℹ 9,953 more rows
# ℹ 1 more variable: ess_tail <num>

We have some basic HMC-based validity statistics we can check.

Code
pnbd_short_onehierlambda2_stanfit$cmdstan_diagnose()
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda2-1.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda2-2.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda2-3.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehierlambda2-4.csv not found
No valid input files, exiting.

2.2 Visual Diagnostics of the Sample Validity

Now that we have a sample from the posterior distribution we need to create a few different visualisations of the diagnostics.

Code
parameter_subset <- c(
  "lambda_mn",
  "lambda[1]", "lambda[2]", "lambda[3]", "lambda[4]",
  "mu[1]",     "mu[2]",     "mu[3]",     "mu[4]"
  )

pnbd_short_onehierlambda2_stanfit$draws(inc_warmup = FALSE) |>
  mcmc_trace(pars = parameter_subset) +
  expand_limits(y = 0) +
  labs(
    x = "Iteration",
    y = "Value",
    title = "Traceplot of Sample of Lambda and Mu Values"
    ) +
  theme(axis.text.x = element_text(size = 10))

We also check \(N_{eff}\) as a quick diagnostic of the fit.

Code
pnbd_short_onehierlambda2_stanfit |>
  neff_ratio(pars = c("lambda", "mu")) |>
  mcmc_neff() +
    ggtitle("Plot of Parameter Effective Sample Sizes")

2.3 Assess the Model

As we intend to run the same logic to assess each of our models, we have combined all this logic into a single function run_model_assessment, to run the simulations and combine the datasets.

Code
pnbd_stanfit <- pnbd_short_onehierlambda2_stanfit |>
  recover_types(customer_fit_stats_tbl)

pnbd_short_onehierlambda2_assess_data_lst <- run_model_assessment(
  model_stanfit    = pnbd_stanfit,
  insample_tbl     = customer_fit_subset_tbl,
  fit_label        = "pnbd_short_onehierlambda2",
  fit_end_dttm     = use_fit_end_date     |> as.POSIXct(),
  valid_start_dttm = use_valid_start_date |> as.POSIXct(),
  valid_end_dttm   = use_valid_end_date   |> as.POSIXct(),
  sim_seed         = 4210
  )

pnbd_short_onehierlambda2_assess_data_lst |> glimpse()
List of 5
 $ model_fit_index_filepath     : 'glue' chr "data/pnbd_short_onehierlambda2_assess_fit_index_tbl.rds"
 $ model_valid_index_filepath   : 'glue' chr "data/pnbd_short_onehierlambda2_assess_valid_index_tbl.rds"
 $ model_simstats_filepath      : 'glue' chr "data/pnbd_short_onehierlambda2_assess_model_simstats_tbl.rds"
 $ model_fit_simstats_filepath  : 'glue' chr "data/pnbd_short_onehierlambda2_assess_fit_simstats_tbl.rds"
 $ model_valid_simstats_filepath: 'glue' chr "data/pnbd_short_onehierlambda2_assess_valid_simstats_tbl.rds"

2.3.1 Check In-Sample Data Validation

We first check the model against the in-sample data.

Code
simdata_tbl <- pnbd_short_onehierlambda2_assess_data_lst |>
  use_series(model_fit_simstats_filepath) |>
  read_rds()

insample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_fit_subset_tbl,
  simdata_tbl = simdata_tbl
  )

insample_plots_lst$multi_plot |> print()

Code
insample_plots_lst$total_plot |> print()

Code
insample_plots_lst$quant_plot |> print()

This fit looks reasonable and appears to capture most of the aspects of the data used to fit it. Given that this is a synthetic dataset, this is not surprising, but at least we appreciate that our model is valid.

2.3.2 Check Out-of-Sample Data Validation

We now repeat for the out-of-sample data.

Code
simdata_tbl <- pnbd_short_onehierlambda1_assess_data_lst |>
  use_series(model_valid_simstats_filepath) |>
  read_rds()

outsample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_valid_subset_tbl,
  simdata_tbl = simdata_tbl
  )

outsample_plots_lst$multi_plot |> print()

Code
outsample_plots_lst$total_plot |> print()

Code
outsample_plots_lst$quant_plot |> print()

As for our short time frame data, overall our model is working well.

3 Fit First Hierarchical Mu Model

We now construct the same hierarchical model but based around mu_mn.

3.1 Compile and Fit Stan Model

We compile this model using CmdStanR.

Code
pnbd_onehiermu_stanmodel <- cmdstan_model(
  "stan_code/pnbd_onehier_mu.stan",
  include_paths =   stan_codedir,
  pedantic      =           TRUE,
  dir           =  stan_modeldir
  )

We then use this compiled model with our data to produce a fit of the data.

Code
stan_modelname <- "pnbd_short_onehiermu1"
stanfit_prefix <- str_c("fit_", stan_modelname)
stanfit_seed   <- stanfit_seed + 1

stanfit_object_file <- glue("data/{stanfit_prefix}_stanfit.rds")


stan_data_lst <- customer_fit_stats_tbl |>
  select(customer_id, x, t_x, T_cal) |>
  compose_data(
    hier_mu_mn_p1 = 0.50,
    hier_mu_mn_p2 = 1.00,

    lambda_mn     = 0.25,
    lambda_cv     = 1.00,

    mu_cv         = 1.00

    )

if(!file_exists(stanfit_object_file)) {
  pnbd_short_onehiermu1_stanfit <- pnbd_onehiermu_stanmodel$sample(
    data            =                stan_data_lst,
    chains          =                            4,
    iter_warmup     =                          500,
    iter_sampling   =                          500,
    seed            =                 stanfit_seed,
    save_warmup     =                         TRUE,
    output_dir      =                stan_modeldir,
    output_basename =               stanfit_prefix,
    )
  
  pnbd_short_onehiermu1_stanfit$save_object(stanfit_object_file, compress = "gzip")

} else {
  pnbd_short_onehiermu1_stanfit <- read_rds(stanfit_object_file)
}

pnbd_short_onehiermu1_stanfit$summary()
# A tibble: 9,963 × 10
   variable       mean   median      sd     mad       q5      q95  rhat ess_bulk
   <chr>         <num>    <num>   <num>   <num>    <num>    <num> <num>    <num>
 1 lp__       -4.38e+4 -4.38e+4 6.20e+1 6.43e+1 -4.39e+4 -4.37e+4  1.01     683.
 2 mu_mn       1.13e-1  1.13e-1 4.47e-3 4.49e-3  1.06e-1  1.21e-1  1.01     585.
 3 lambda[1]   4.45e-1  4.27e-1 1.53e-1 1.48e-1  2.28e-1  7.29e-1  1.00    2775.
 4 lambda[2]   2.08e-1  1.81e-1 1.31e-1 1.16e-1  5.17e-2  4.72e-1  1.00    2112.
 5 lambda[3]   2.65e-1  2.16e-1 2.04e-1 1.69e-1  3.68e-2  6.57e-1  1.00    2428.
 6 lambda[4]   1.38e-1  8.69e-2 1.54e-1 9.84e-2  4.07e-3  4.37e-1  1.00    1672.
 7 lambda[5]   4.94e-1  4.45e-1 2.64e-1 2.35e-1  1.60e-1  9.89e-1  1.00    1978.
 8 lambda[6]   2.46e-1  1.95e-1 1.97e-1 1.48e-1  3.69e-2  6.13e-1  1.00    2000.
 9 lambda[7]   1.40e-1  8.23e-2 1.62e-1 9.50e-2  4.18e-3  4.60e-1  1.00    1494.
10 lambda[8]   1.63e-1  1.54e-1 6.80e-2 6.37e-2  6.83e-2  2.85e-1  1.00    2762.
# ℹ 9,953 more rows
# ℹ 1 more variable: ess_tail <num>

We have some basic HMC-based validity statistics we can check.

Code
pnbd_short_onehiermu1_stanfit$cmdstan_diagnose()
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu1-1.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu1-2.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu1-3.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu1-4.csv not found
No valid input files, exiting.

3.2 Visual Diagnostics of the Sample Validity

Now that we have a sample from the posterior distribution we need to create a few different visualisations of the diagnostics.

Code
parameter_subset <- c(
  "mu_mn",
  "lambda[1]", "lambda[2]", "lambda[3]", "lambda[4]",
  "mu[1]",     "mu[2]",     "mu[3]",     "mu[4]"
  )

pnbd_short_onehiermu1_stanfit$draws(inc_warmup = FALSE) |>
  mcmc_trace(pars = parameter_subset) +
  expand_limits(y = 0) +
  labs(
    x = "Iteration",
    y = "Value",
    title = "Traceplot of Sample of Lambda and Mu Values"
    ) +
  theme(axis.text.x = element_text(size = 10))

We also check \(N_{eff}\) as a quick diagnostic of the fit.

Code
pnbd_short_onehiermu1_stanfit |>
  neff_ratio(pars = c("lambda", "mu")) |>
  mcmc_neff() +
    ggtitle("Plot of Parameter Effective Sample Sizes")

3.3 Assess the Model

As we intend to run the same logic to assess each of our models, we have combined all this logic into a single function run_model_assessment, to run the simulations and combine the datasets.

Code
pnbd_stanfit <- pnbd_short_onehiermu1_stanfit |>
  recover_types(customer_fit_stats_tbl)

pnbd_short_onehiermu1_assess_data_lst <- run_model_assessment(
  model_stanfit    = pnbd_stanfit,
  insample_tbl     = customer_fit_subset_tbl,
  fit_label        = "pnbd_short_onehiermu1",
  fit_end_dttm     = use_fit_end_date     |> as.POSIXct(),
  valid_start_dttm = use_valid_start_date |> as.POSIXct(),
  valid_end_dttm   = use_valid_end_date   |> as.POSIXct(),
  sim_seed         = 4210
  )

pnbd_short_onehiermu1_assess_data_lst |> glimpse()
List of 5
 $ model_fit_index_filepath     : 'glue' chr "data/pnbd_short_onehiermu1_assess_fit_index_tbl.rds"
 $ model_valid_index_filepath   : 'glue' chr "data/pnbd_short_onehiermu1_assess_valid_index_tbl.rds"
 $ model_simstats_filepath      : 'glue' chr "data/pnbd_short_onehiermu1_assess_model_simstats_tbl.rds"
 $ model_fit_simstats_filepath  : 'glue' chr "data/pnbd_short_onehiermu1_assess_fit_simstats_tbl.rds"
 $ model_valid_simstats_filepath: 'glue' chr "data/pnbd_short_onehiermu1_assess_valid_simstats_tbl.rds"

3.3.1 Check In-Sample Data Validation

We first check the model against the in-sample data.

Code
simdata_tbl <- pnbd_short_onehiermu1_assess_data_lst |>
  use_series(model_fit_simstats_filepath) |>
  read_rds()

insample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_fit_subset_tbl,
  simdata_tbl = simdata_tbl
  )

insample_plots_lst$multi_plot |> print()

Code
insample_plots_lst$total_plot |> print()

Code
insample_plots_lst$quant_plot |> print()

This fit looks reasonable and appears to capture most of the aspects of the data used to fit it. Given that this is a synthetic dataset, this is not surprising, but at least we appreciate that our model is valid.

3.3.2 Check Out-of-Sample Data Validation

We now repeat for the out-of-sample data.

Code
simdata_tbl <- pnbd_short_onehierlambda1_assess_data_lst |>
  use_series(model_valid_simstats_filepath) |>
  read_rds()

outsample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_valid_subset_tbl,
  simdata_tbl = simdata_tbl
  )

outsample_plots_lst$multi_plot |> print()

Code
outsample_plots_lst$total_plot |> print()

Code
outsample_plots_lst$quant_plot |> print()

As for our short time frame data, overall our model is working well.

4 Fit Second Hierarchical Mu Model

In this model, we are going with a broadly similar model but we are instead using a different mean for our hierarchical prior.

4.1 Fit Stan Model

We now want to fit the model to our data using this alternative prior for lambda_mn.

Code
stan_modelname <- "pnbd_short_onehiermu2"
stanfit_prefix <- str_c("fit_", stan_modelname)
stanfit_seed   <- stanfit_seed + 1

stanfit_object_file <- glue("data/{stanfit_prefix}_stanfit.rds")


stan_data_lst <- customer_fit_stats_tbl |>
  select(customer_id, x, t_x, T_cal) |>
  compose_data(
    hier_mu_mn_p1 = 0.25,
    hier_mu_mn_p2 = 1.00,

    lambda_mn     = 0.25,
    lambda_cv     = 1.00,

    mu_cv         = 1.00
    )

if(!file_exists(stanfit_object_file)) {
  pnbd_short_onehiermu2_stanfit <- pnbd_onehiermu_stanmodel$sample(
    data            =                stan_data_lst,
    chains          =                            4,
    iter_warmup     =                          500,
    iter_sampling   =                          500,
    seed            =                 stanfit_seed,
    save_warmup     =                         TRUE,
    output_dir      =                stan_modeldir,
    output_basename =               stanfit_prefix,
    )
  
  pnbd_short_onehiermu2_stanfit$save_object(stanfit_object_file, compress = "gzip")

} else {
  pnbd_short_onehiermu2_stanfit <- read_rds(stanfit_object_file)
}

pnbd_short_onehiermu2_stanfit$summary()
# A tibble: 9,963 × 10
   variable       mean   median      sd     mad       q5      q95  rhat ess_bulk
   <chr>         <num>    <num>   <num>   <num>    <num>    <num> <num>    <num>
 1 lp__       -4.38e+4 -4.38e+4 6.49e+1 6.69e+1 -4.39e+4 -4.37e+4  1.01     593.
 2 mu_mn       1.13e-1  1.13e-1 4.39e-3 4.38e-3  1.06e-1  1.20e-1  1.01     384.
 3 lambda[1]   4.47e-1  4.27e-1 1.54e-1 1.48e-1  2.27e-1  7.37e-1  1.00    3278.
 4 lambda[2]   2.11e-1  1.80e-1 1.31e-1 1.16e-1  5.67e-2  4.55e-1  1.01    2523.
 5 lambda[3]   2.63e-1  2.06e-1 2.09e-1 1.69e-1  4.08e-2  6.84e-1  1.00    1921.
 6 lambda[4]   1.45e-1  8.38e-2 1.69e-1 9.54e-2  5.07e-3  4.89e-1  1.00    1713.
 7 lambda[5]   4.91e-1  4.43e-1 2.73e-1 2.55e-1  1.53e-1  1.00e+0  1.00    2035.
 8 lambda[6]   2.44e-1  2.01e-1 1.99e-1 1.55e-1  3.46e-2  6.19e-1  1.01    2510.
 9 lambda[7]   1.37e-1  8.37e-2 1.53e-1 9.09e-2  5.49e-3  4.47e-1  1.00    1927.
10 lambda[8]   1.64e-1  1.56e-1 6.82e-2 6.40e-2  6.82e-2  2.88e-1  1.00    3151.
# ℹ 9,953 more rows
# ℹ 1 more variable: ess_tail <num>

We have some basic HMC-based validity statistics we can check.

Code
pnbd_short_onehiermu2_stanfit$cmdstan_diagnose()
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu2-1.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu2-2.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu2-3.csv not found
File /home/rstudio/btydwork/stan_models/fit_pnbd_init_short_onehiermu2-4.csv not found
No valid input files, exiting.

4.2 Visual Diagnostics of the Sample Validity

Now that we have a sample from the posterior distribution we need to create a few different visualisations of the diagnostics.

Code
parameter_subset <- c(
  "mu_mn",
  "lambda[1]", "lambda[2]", "lambda[3]", "lambda[4]",
  "mu[1]",     "mu[2]",     "mu[3]",     "mu[4]"
  )

pnbd_short_onehiermu2_stanfit$draws(inc_warmup = FALSE) |>
  mcmc_trace(pars = parameter_subset) +
  expand_limits(y = 0) +
  labs(
    x = "Iteration",
    y = "Value",
    title = "Traceplot of Sample of Lambda and Mu Values"
    ) +
  theme(axis.text.x = element_text(size = 10))

We also check \(N_{eff}\) as a quick diagnostic of the fit.

Code
pnbd_short_onehiermu2_stanfit |>
  neff_ratio(pars = c("lambda", "mu")) |>
  mcmc_neff() +
    ggtitle("Plot of Parameter Effective Sample Sizes")

4.3 Assess the Model

As we intend to run the same logic to assess each of our models, we have combined all this logic into a single function run_model_assessment, to run the simulations and combine the datasets.

Code
pnbd_stanfit <- pnbd_short_onehiermu2_stanfit |>
  recover_types(customer_fit_stats_tbl)

pnbd_short_onehiermu2_assess_data_lst <- run_model_assessment(
  model_stanfit    = pnbd_stanfit,
  insample_tbl     = customer_fit_subset_tbl,
  fit_label        = "pnbd_short_onehiermu2",
  fit_end_dttm     = use_fit_end_date     |> as.POSIXct(),
  valid_start_dttm = use_valid_start_date |> as.POSIXct(),
  valid_end_dttm   = use_valid_end_date   |> as.POSIXct(),
  sim_seed         = 4210
  )

pnbd_short_onehiermu2_assess_data_lst |> glimpse()
List of 5
 $ model_fit_index_filepath     : 'glue' chr "data/pnbd_short_onehiermu2_assess_fit_index_tbl.rds"
 $ model_valid_index_filepath   : 'glue' chr "data/pnbd_short_onehiermu2_assess_valid_index_tbl.rds"
 $ model_simstats_filepath      : 'glue' chr "data/pnbd_short_onehiermu2_assess_model_simstats_tbl.rds"
 $ model_fit_simstats_filepath  : 'glue' chr "data/pnbd_short_onehiermu2_assess_fit_simstats_tbl.rds"
 $ model_valid_simstats_filepath: 'glue' chr "data/pnbd_short_onehiermu2_assess_valid_simstats_tbl.rds"

4.3.1 Check In-Sample Data Validation

We first check the model against the in-sample data.

Code
simdata_tbl <- pnbd_short_onehiermu2_assess_data_lst |>
  use_series(model_fit_simstats_filepath) |>
  read_rds()

insample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_fit_subset_tbl,
  simdata_tbl = simdata_tbl
  )

insample_plots_lst$multi_plot |> print()

Code
insample_plots_lst$total_plot |> print()

Code
insample_plots_lst$quant_plot |> print()

This fit looks reasonable and appears to capture most of the aspects of the data used to fit it. Given that this is a synthetic dataset, this is not surprising, but at least we appreciate that our model is valid.

4.3.2 Check Out-of-Sample Data Validation

We now repeat for the out-of-sample data.

Code
simdata_tbl <- pnbd_short_onehiermu1_assess_data_lst |>
  use_series(model_valid_simstats_filepath) |>
  read_rds()

outsample_plots_lst <- create_model_assessment_plots(
  obsdata_tbl = customer_valid_subset_tbl,
  simdata_tbl = simdata_tbl
  )

outsample_plots_lst$multi_plot |> print()

Code
outsample_plots_lst$total_plot |> print()

Code
outsample_plots_lst$quant_plot |> print()

As for our short time frame data, overall our model is working well.

5 Compare Model Outputs

We have looked at each of the models individually, but it is also worth looking at each of the models as a group.

Code
calculate_simulation_statistics <- function(file_rds) {
  simdata_tbl <- read_rds(file_rds)
  
  multicount_cust_tbl <- simdata_tbl |>
    filter(sim_tnx_count > 0) |>
    count(draw_id, name = "multicust_count")
  
  totaltnx_data_tbl <- simdata_tbl |>
    count(draw_id, wt = sim_tnx_count, name = "simtnx_count")
  
  simstats_tbl <- multicount_cust_tbl |>
    inner_join(totaltnx_data_tbl, by = "draw_id")
  
  return(simstats_tbl)
}
Code
obs_fit_customer_count <- customer_fit_subset_tbl |>
  filter(tnx_count > 0) |>
  nrow()

obs_valid_customer_count <- customer_valid_subset_tbl |>
  filter(tnx_count > 0) |>
  nrow()

obs_fit_total_count <- customer_fit_subset_tbl |>
  pull(tnx_count) |>
  sum()

obs_valid_total_count <- customer_valid_subset_tbl |>
  pull(tnx_count) |>
  sum()


obs_stats_tbl <- tribble(
  ~assess_type, ~name,               ~obs_value,
  "fit",        "multicust_count",   obs_fit_customer_count,
  "fit",        "simtnx_count",      obs_fit_total_count,
  "valid",      "multicust_count",   obs_valid_customer_count,
  "valid",      "simtnx_count",      obs_valid_total_count
  )


model_assess_tbl <- dir_ls("data", regexp = "pnbd_short_(one|fixed).*_assess_.*simstats") |>
  enframe(name = NULL, value = "file_path") |>
  filter(str_detect(file_path, "_assess_model_", negate = TRUE)) |>
  mutate(
    model_label = str_replace(file_path, "data/pnbd_short_(.*?)_assess_.*", "\\1"),
    assess_type = if_else(str_detect(file_path, "_assess_fit_"), "fit", "valid"),
    
    sim_data = map(
      file_path, calculate_simulation_statistics,
      
      .progress = "calculate_simulation_statistics"
      )
    )

model_assess_tbl |> glimpse()
Rows: 16
Columns: 4
$ file_path   <fs::path> "data/pnbd_short_fixed1_assess_fit_simstats_tbl.rds",…
$ model_label <chr> "fixed1", "fixed1", "fixed2", "fixed2", "fixed3", "fixed3"…
$ assess_type <chr> "fit", "valid", "fit", "valid", "fit", "valid", "fit", "va…
$ sim_data    <list> [<tbl_df[2000 x 3]>], [<tbl_df[2000 x 3]>], [<tbl_df[2000…
Code
model_assess_summstat_tbl <- model_assess_tbl |>
  select(model_label, assess_type, sim_data) |>
  unnest(sim_data) |>
  pivot_longer(
    cols = !c(model_label, assess_type, draw_id)
    ) |>
  group_by(model_label, assess_type, name) |>
  summarise(
    .groups = "drop",
    
    mean_val = mean(value),
    p10 = quantile(value, 0.10),
    p25 = quantile(value, 0.25),
    p50 = quantile(value, 0.50),
    p75 = quantile(value, 0.75),
    p90 = quantile(value, 0.90)
    )

model_assess_summstat_tbl |> glimpse()
Rows: 32
Columns: 9
$ model_label <chr> "fixed1", "fixed1", "fixed1", "fixed1", "fixed2", "fixed2"…
$ assess_type <chr> "fit", "fit", "valid", "valid", "fit", "fit", "valid", "va…
$ name        <chr> "multicust_count", "simtnx_count", "multicust_count", "sim…
$ mean_val    <dbl> 601.6880, 4081.1590, 158.9110, 1559.5810, 671.4355, 3094.8…
$ p10         <dbl> 583.0, 3819.0, 149.0, 1399.0, 653.0, 2907.9, 110.9, 686.0,…
$ p25         <dbl> 592.00, 3936.00, 153.00, 1470.00, 662.00, 2996.00, 115.00,…
$ p50         <dbl> 602.0, 4079.0, 159.0, 1553.0, 672.0, 3095.0, 119.0, 787.0,…
$ p75         <dbl> 612.00, 4220.00, 165.00, 1647.00, 681.00, 3194.00, 124.00,…
$ p90         <dbl> 620.0, 4357.0, 169.0, 1733.1, 689.0, 3282.0, 128.0, 897.0,…
Code
#! echo: TRUE

ggplot(model_assess_summstat_tbl) +
  geom_errorbar(
    aes(x = model_label, ymin = p10, ymax = p90), width = 0
    ) +
  geom_errorbar(
    aes(x = model_label, ymin = p25, ymax = p75), width = 0, linewidth = 3
    ) +
  geom_hline(
    aes(yintercept = obs_value),
    data = obs_stats_tbl, colour = "red"
    ) +
  scale_y_continuous(labels = label_comma()) +
  expand_limits(y = 0) +
  facet_wrap(
    vars(assess_type, name), scale = "free_y"
    ) +
  labs(
    x = "Model",
    y = "Count",
    title = "Comparison Plot for the Different Models"
    ) +
  theme(
    axis.text.x = element_text(angle = 20, vjust = 0.5, size = 8)
    )

5.1 Write Assessment Data to Disk

We now want to save the assessment data to disk.

Code
model_assess_tbl |> write_rds("data/assess_data_pnbd_short_onehier_tbl.rds")

R Environment

Code
options(width = 120L)
sessioninfo::session_info()
─ Session info ───────────────────────────────────────────────────────────────────────────────────────────────────────
 setting  value
 version  R version 4.3.1 (2023-06-16)
 os       Ubuntu 22.04.3 LTS
 system   x86_64, linux-gnu
 ui       X11
 language (EN)
 collate  en_US.UTF-8
 ctype    en_US.UTF-8
 tz       Europe/Dublin
 date     2023-11-11
 pandoc   3.1.1 @ /usr/local/bin/ (via rmarkdown)

─ Packages ───────────────────────────────────────────────────────────────────────────────────────────────────────────
 package        * version    date (UTC) lib source
 abind            1.4-5      2016-07-21 [1] RSPM (R 4.3.0)
 arrayhelpers     1.1-0      2020-02-04 [1] RSPM (R 4.3.0)
 backports        1.4.1      2021-12-13 [1] RSPM (R 4.3.0)
 base64enc        0.1-3      2015-07-28 [1] RSPM (R 4.3.0)
 bayesplot      * 1.10.0     2022-11-16 [1] RSPM (R 4.3.0)
 bit              4.0.5      2022-11-15 [1] RSPM (R 4.3.0)
 bit64            4.0.5      2020-08-30 [1] RSPM (R 4.3.0)
 bridgesampling   1.1-2      2021-04-16 [1] RSPM (R 4.3.0)
 brms           * 2.20.4     2023-09-25 [1] RSPM (R 4.3.0)
 Brobdingnag      1.2-9      2022-10-19 [1] RSPM (R 4.3.0)
 cachem           1.0.8      2023-05-01 [1] RSPM (R 4.3.0)
 callr            3.7.3      2022-11-02 [1] RSPM (R 4.3.0)
 checkmate        2.3.0      2023-10-25 [1] RSPM (R 4.3.0)
 cli              3.6.1      2023-03-23 [1] RSPM (R 4.3.0)
 cmdstanr       * 0.6.0.9000 2023-11-07 [1] Github (stan-dev/cmdstanr@a13c798)
 coda             0.19-4     2020-09-30 [1] RSPM (R 4.3.0)
 codetools        0.2-19     2023-02-01 [2] CRAN (R 4.3.1)
 colorspace       2.1-0      2023-01-23 [1] RSPM (R 4.3.0)
 colourpicker     1.3.0      2023-08-21 [1] RSPM (R 4.3.0)
 conflicted     * 1.2.0      2023-02-01 [1] RSPM (R 4.3.0)
 cowplot        * 1.1.1      2020-12-30 [1] RSPM (R 4.3.0)
 crayon           1.5.2      2022-09-29 [1] RSPM (R 4.3.0)
 crosstalk        1.2.0      2021-11-04 [1] RSPM (R 4.3.0)
 curl             5.1.0      2023-10-02 [1] RSPM (R 4.3.0)
 digest           0.6.33     2023-07-07 [1] RSPM (R 4.3.0)
 directlabels   * 2023.8.25  2023-09-01 [1] RSPM (R 4.3.0)
 distributional   0.3.2      2023-03-22 [1] RSPM (R 4.3.0)
 dplyr          * 1.1.3      2023-09-03 [1] RSPM (R 4.3.0)
 DT               0.30       2023-10-05 [1] RSPM (R 4.3.0)
 dygraphs         1.1.1.6    2018-07-11 [1] RSPM (R 4.3.0)
 ellipsis         0.3.2      2021-04-29 [1] RSPM (R 4.3.0)
 evaluate         0.22       2023-09-29 [1] RSPM (R 4.3.0)
 fansi            1.0.5      2023-10-08 [1] RSPM (R 4.3.0)
 farver           2.1.1      2022-07-06 [1] RSPM (R 4.3.0)
 fastmap          1.1.1      2023-02-24 [1] RSPM (R 4.3.0)
 forcats        * 1.0.0      2023-01-29 [1] RSPM (R 4.3.0)
 fs             * 1.6.3      2023-07-20 [1] RSPM (R 4.3.0)
 furrr          * 0.3.1      2022-08-15 [1] RSPM (R 4.3.0)
 future         * 1.33.0     2023-07-01 [1] RSPM (R 4.3.0)
 generics         0.1.3      2022-07-05 [1] RSPM (R 4.3.0)
 ggdist           3.3.0      2023-05-13 [1] RSPM (R 4.3.0)
 ggplot2        * 3.4.4      2023-10-12 [1] RSPM (R 4.3.0)
 globals          0.16.2     2022-11-21 [1] RSPM (R 4.3.0)
 glue           * 1.6.2      2022-02-24 [1] RSPM (R 4.3.0)
 gridExtra        2.3        2017-09-09 [1] RSPM (R 4.3.0)
 gtable           0.3.4      2023-08-21 [1] RSPM (R 4.3.0)
 gtools           3.9.4      2022-11-27 [1] RSPM (R 4.3.0)
 hms              1.1.3      2023-03-21 [1] RSPM (R 4.3.0)
 htmltools        0.5.6.1    2023-10-06 [1] RSPM (R 4.3.0)
 htmlwidgets      1.6.2      2023-03-17 [1] RSPM (R 4.3.0)
 httpuv           1.6.12     2023-10-23 [1] RSPM (R 4.3.0)
 igraph           1.5.1      2023-08-10 [1] RSPM (R 4.3.0)
 inline           0.3.19     2021-05-31 [1] RSPM (R 4.3.0)
 jsonlite         1.8.7      2023-06-29 [1] RSPM (R 4.3.0)
 knitr            1.44       2023-09-11 [1] RSPM (R 4.3.0)
 labeling         0.4.3      2023-08-29 [1] RSPM (R 4.3.0)
 later            1.3.1      2023-05-02 [1] RSPM (R 4.3.0)
 lattice          0.21-8     2023-04-05 [2] CRAN (R 4.3.1)
 lifecycle        1.0.3      2022-10-07 [1] RSPM (R 4.3.0)
 listenv          0.9.0      2022-12-16 [1] RSPM (R 4.3.0)
 loo              2.6.0      2023-03-31 [1] RSPM (R 4.3.0)
 lubridate      * 1.9.3      2023-09-27 [1] RSPM (R 4.3.0)
 magrittr       * 2.0.3      2022-03-30 [1] RSPM (R 4.3.0)
 markdown         1.11       2023-10-19 [1] RSPM (R 4.3.0)
 Matrix           1.5-4.1    2023-05-18 [2] CRAN (R 4.3.1)
 matrixStats      1.0.0      2023-06-02 [1] RSPM (R 4.3.0)
 memoise          2.0.1      2021-11-26 [1] RSPM (R 4.3.0)
 mime             0.12       2021-09-28 [1] RSPM (R 4.3.0)
 miniUI           0.1.1.1    2018-05-18 [1] RSPM (R 4.3.0)
 munsell          0.5.0      2018-06-12 [1] RSPM (R 4.3.0)
 mvtnorm          1.2-3      2023-08-25 [1] RSPM (R 4.3.0)
 nlme             3.1-162    2023-01-31 [2] CRAN (R 4.3.1)
 parallelly       1.36.0     2023-05-26 [1] RSPM (R 4.3.0)
 pillar           1.9.0      2023-03-22 [1] RSPM (R 4.3.0)
 pkgbuild         1.4.2      2023-06-26 [1] RSPM (R 4.3.0)
 pkgconfig        2.0.3      2019-09-22 [1] RSPM (R 4.3.0)
 plyr             1.8.9      2023-10-02 [1] RSPM (R 4.3.0)
 posterior      * 1.4.1      2023-03-14 [1] RSPM (R 4.3.0)
 prettyunits      1.2.0      2023-09-24 [1] RSPM (R 4.3.0)
 processx         3.8.2      2023-06-30 [1] RSPM (R 4.3.0)
 promises         1.2.1      2023-08-10 [1] RSPM (R 4.3.0)
 ps               1.7.5      2023-04-18 [1] RSPM (R 4.3.0)
 purrr          * 1.0.2      2023-08-10 [1] RSPM (R 4.3.0)
 quadprog         1.5-8      2019-11-20 [1] RSPM (R 4.3.0)
 QuickJSR         1.0.7      2023-10-15 [1] RSPM (R 4.3.0)
 R6               2.5.1      2021-08-19 [1] RSPM (R 4.3.0)
 Rcpp           * 1.0.11     2023-07-06 [1] RSPM (R 4.3.0)
 RcppParallel     5.1.7      2023-02-27 [1] RSPM (R 4.3.0)
 readr          * 2.1.4      2023-02-10 [1] RSPM (R 4.3.0)
 reshape2         1.4.4      2020-04-09 [1] RSPM (R 4.3.0)
 rlang          * 1.1.1      2023-04-28 [1] RSPM (R 4.3.0)
 rmarkdown        2.25       2023-09-18 [1] RSPM (R 4.3.0)
 rstan            2.32.3     2023-10-15 [1] RSPM (R 4.3.0)
 rstantools       2.3.1.1    2023-07-18 [1] RSPM (R 4.3.0)
 rstudioapi       0.15.0     2023-07-07 [1] RSPM (R 4.3.0)
 rsyslog        * 1.0.3      2023-05-08 [1] RSPM (R 4.3.0)
 scales         * 1.2.1      2022-08-20 [1] RSPM (R 4.3.0)
 sessioninfo      1.2.2      2021-12-06 [1] RSPM (R 4.3.0)
 shiny            1.7.5.1    2023-10-14 [1] RSPM (R 4.3.0)
 shinyjs          2.1.0      2021-12-23 [1] RSPM (R 4.3.0)
 shinystan        2.6.0      2022-03-03 [1] RSPM (R 4.3.0)
 shinythemes      1.2.0      2021-01-25 [1] RSPM (R 4.3.0)
 StanHeaders      2.26.28    2023-09-07 [1] RSPM (R 4.3.0)
 stringi          1.7.12     2023-01-11 [1] RSPM (R 4.3.0)
 stringr        * 1.5.0      2022-12-02 [1] RSPM (R 4.3.0)
 svUnit           1.0.6      2021-04-19 [1] RSPM (R 4.3.0)
 tensorA          0.36.2     2020-11-19 [1] RSPM (R 4.3.0)
 threejs          0.3.3      2020-01-21 [1] RSPM (R 4.3.0)
 tibble         * 3.2.1      2023-03-20 [1] RSPM (R 4.3.0)
 tidybayes      * 3.0.6      2023-08-12 [1] RSPM (R 4.3.0)
 tidyr          * 1.3.0      2023-01-24 [1] RSPM (R 4.3.0)
 tidyselect       1.2.0      2022-10-10 [1] RSPM (R 4.3.0)
 tidyverse      * 2.0.0      2023-02-22 [1] RSPM (R 4.3.0)
 timechange       0.2.0      2023-01-11 [1] RSPM (R 4.3.0)
 tzdb             0.4.0      2023-05-12 [1] RSPM (R 4.3.0)
 utf8             1.2.4      2023-10-22 [1] RSPM (R 4.3.0)
 V8               4.4.0      2023-10-09 [1] RSPM (R 4.3.0)
 vctrs            0.6.4      2023-10-12 [1] RSPM (R 4.3.0)
 vroom            1.6.4      2023-10-02 [1] RSPM (R 4.3.0)
 withr            2.5.1      2023-09-26 [1] RSPM (R 4.3.0)
 xfun             0.40       2023-08-09 [1] RSPM (R 4.3.0)
 xtable           1.8-4      2019-04-21 [1] RSPM (R 4.3.0)
 xts              0.13.1     2023-04-16 [1] RSPM (R 4.3.0)
 yaml             2.3.7      2023-01-23 [1] RSPM (R 4.3.0)
 zoo              1.8-12     2023-04-13 [1] RSPM (R 4.3.0)

 [1] /usr/local/lib/R/site-library
 [2] /usr/local/lib/R/library

──────────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Code
options(width = 80L)